1
$\begingroup$

I have two continuous variables: $X1$ and $X2$, both have a positive correlation on the dependent variable $y$ (continuous). I found that the interaction term $(X1*X2)$ is statistically significant for $p\lt(0.00)$ when added to the model. The final model is the following:

$$y=aX_1+bX_2-c(X_1*X_2)$$

Where $a$, $b$, and $c$ are the regression coefficients. However, I am wondering why the regression coefficient for $c$ of the interaction term is negative? What does it mean?

If I only add the interaction term $(X1*X2)$ to the model why is the coefficient positive when if I add it with $(X1)$ and $(X2)$ the regression coefficient becomes negative? It doesn't make sense!

$\endgroup$

1 Answer 1

1
$\begingroup$

If the following statement is true, Then it means y should increase as either X1 or X2 increases.

I have 2 continuous variables; X1 and X2, both have a positive correlation on the dependent variable y (continuous)

This is your final model:

$y=aX_1+bX_2-c(X_1*X_2)$

but I wonder why the regression coefficient c of the interaction term is negative? what does it mean?

you have a negative sign before the c coefficient which means it tries to decrease y as X1,X2 increases but the data necessitates that it should increase. Hence c is negative.

why if I add only the interaction term (X1*X2) to the model, the coefficient is positive while if I add it with (X1) and (X2) the regression coefficient becomes negative? it doesn't make sense!

By adding just X1*X2 to your does it look like the equation below?

$y=c(X_1*X_2)$

Then it makes sense only if c is positive if not then Y will decrease with increase in X1, X2. It makes sense.

$\endgroup$
3
  • $\begingroup$ Thank for your answer , is it mean that X1 is function of X2 and X2 is function of X1 ? $\endgroup$ Nov 12, 2020 at 22:48
  • 1
    $\begingroup$ @YazanAlatoom No X1 and X2 are independent variables and Y is an independent variable. If you find the answer useful, then you could upvote or accept it $\endgroup$ Nov 13, 2020 at 10:41
  • $\begingroup$ the final model is the following: Y=1.956+0.102*X1+0.830*X2-0.063*X1*X2 , the range of X1:1-10 , X2:0.01-6 , in some cases value of Y is lower when some value of X1 and X2 is high than when the value of X1 AND X2 is low $\endgroup$ Nov 13, 2020 at 10:52

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.